Multimodal sentiment analysis aims to understand emotions from text,speech,and video data.However,current methods often overlook the dominant role of text and suffer from feature loss during integration.Given the vary...Multimodal sentiment analysis aims to understand emotions from text,speech,and video data.However,current methods often overlook the dominant role of text and suffer from feature loss during integration.Given the varying importance of each modality across different contexts,a central and pressing challenge in multimodal sentiment analysis lies in maximizing the use of rich intra-modal features while minimizing information loss during the fusion process.In response to these critical limitations,we propose a novel framework that integrates spatial position encoding and fusion embedding modules to address these issues.In our model,text is treated as the core modality,while speech and video features are selectively incorporated through a unique position-aware fusion process.The spatial position encoding strategy preserves the internal structural information of speech and visual modalities,enabling the model to capture localized intra-modal dependencies that are often overlooked.This design enhances the richness and discriminative power of the fused representation,enabling more accurate and context-aware sentiment prediction.Finally,we conduct comprehensive evaluations on two widely recognized standard datasets in the field—CMU-MOSI and CMU-MOSEI to validate the performance of the proposed model.The experimental results demonstrate that our model exhibits good performance and effectiveness for sentiment analysis tasks.展开更多
To solve the problem of identification and measurement of two projectiles hitting the target at the same time,this paper proposes a projectile coordinate test method combining three photoelectric encoder detection scr...To solve the problem of identification and measurement of two projectiles hitting the target at the same time,this paper proposes a projectile coordinate test method combining three photoelectric encoder detection screens,and establishes a coordinate calculation model for two projectiles to reach the same detection screen at the same time.The design method of three photoelectric encoder detection screens and the position coordinate recognition algorithm of the blocked array photoelectric detector when projectile passing through the photoelectric encoder detection screen are studied.Using the screen projection method,the intersected linear equation of the projectile and the line laser with the main detection screen as the core coordinate plane is established,and the projectile coordinate data set formed by any two photoelectric encoder detection screens is constructed.The principle of minimum error of coordinate data set is used to determine the coordinates of two projectiles hitting the target at the same time.The rationality and feasibility of the proposed test method are verified by experiments and comparative tests.展开更多
In this paper,a composite numerical scheme is proposed to solve the threedimensional Darcy-Forchheimer miscible displacement problem with positive semi-definite assumptions.A mixed finite element is used for the fow e...In this paper,a composite numerical scheme is proposed to solve the threedimensional Darcy-Forchheimer miscible displacement problem with positive semi-definite assumptions.A mixed finite element is used for the fow equation.The velocity and pressure are computed simultaneously.The accuracy of velocity is improved one order.The concentration equation is solved by using mixed finite element,multi-step difference and upwind approximation.A multi-step method is used to approximate time derivative for improving the accuracy.The upwind approximation and an expanded mixed finite element are adopted to solve the convection and diffusion,respectively.The composite method could compute the diffusion flux and its gradient.It possibly becomes an eficient tool for solving convection-dominated diffusion problems.Firstly,the conservation of mass holds.Secondly,the multi-step method has high accuracy.Thirdly,the upwind approximation could avoid numerical dispersion.Using numerical analysis of a priori estimates and special techniques of differential equations,we give an error estimates for a positive definite problem.Numerical experiments illustrate its computational efficiency and feasibility of application.展开更多
Accurate remaining useful life(RUL)prediction is important in industrial systems.It prevents machines from working under failure conditions,and ensures that the industrial system works reliably and efficiently.Recentl...Accurate remaining useful life(RUL)prediction is important in industrial systems.It prevents machines from working under failure conditions,and ensures that the industrial system works reliably and efficiently.Recently,many deep learning based methods have been proposed to predict RUL.Among these methods,recurrent neural network(RNN)based approaches show a strong capability of capturing sequential information.This allows RNN based methods to perform better than convolutional neural network(CNN)based approaches on the RUL prediction task.In this paper,we question this common paradigm and argue that existing CNN based approaches are not designed according to the classic principles of CNN,which reduces their performances.Additionally,the capacity of capturing sequential information is highly affected by the receptive field of CNN,which is neglected by existing CNN based methods.To solve these problems,we propose a series of new CNNs,which show competitive results to RNN based methods.Compared with RNN,CNN processes the input signals in parallel so that the temporal sequence is not easily determined.To alleviate this issue,a position encoding scheme is developed to enhance the sequential information encoded by a CNN.Hence,our proposed position encoding based CNN called PE-Net is further improved and even performs better than RNN based methods.Extensive experiments are conducted on the C-MAPSS dataset,where our PE-Net shows state-of-the-art performance.展开更多
A method and procedure is presented to reconstruct three-dimensional(3D) positions of scattering centers from multiple synthetic aperture radar(SAR) images. Firstly, two-dimensional(2D) attribute scattering centers of...A method and procedure is presented to reconstruct three-dimensional(3D) positions of scattering centers from multiple synthetic aperture radar(SAR) images. Firstly, two-dimensional(2D) attribute scattering centers of targets are extracted from 2D SAR images. Secondly, similarity measure is developed based on 2D attributed scatter centers' location, type, and radargrammetry principle between multiple SAR images. By this similarity, we can associate 2D scatter centers and then obtain candidate 3D scattering centers. Thirdly, these candidate scattering centers are clustered in 3D space to reconstruct final 3D positions. Compared with presented methods, the proposed method has a capability of describing distributed scattering center, reduces false and missing 3D scattering centers, and has fewer restrictionson modeling data. Finally, results of experiments have demonstrated the effectiveness of the proposed method.展开更多
This paper addresses the problem of assessing and optimizing the acoustic positioning system for underwater target localization with range measurement.We present a new three-dimensional assessment model to evaluate th...This paper addresses the problem of assessing and optimizing the acoustic positioning system for underwater target localization with range measurement.We present a new three-dimensional assessment model to evaluate the optimal geometric beacon formation whether meets user requirements.For mathematical tractability,it is assumed that the measurements of the range between the target and beacons are corrupted with white Gaussian noise with variance,which is distance-dependent.Then,the relationship between DOP parameters and positioning accuracy can be derived by adopting dilution of precision(DOP)parameters in the assessment model.In addition,the optimal geometric beacon formation yielding the best performance can be achieved via minimizing the values of geometric dilution of precision(GDOP)in the case where the target position is known and fixed.Next,in order to ensure that the estimated positioning accuracy on the region of interest satisfies the precision required by the user,geometric positioning accuracy(GPA),horizontal positioning accuracy(HPA)and vertical positioning accuracy(VPA)are utilized to assess the optimal geometric beacon formation.Simulation examples are designed to illustrate the exactness of the conclusion.Unlike other work that only uses GDOP to optimize the formation and cannot assess the performance of the specified size,this new three-dimensional assessment model can evaluate the optimal geometric beacon formation for each dimension of any point in three-dimensional space,which can provide guidance to optimize the performance of each specified dimension.展开更多
In order to achieve the goal that unmanned aerial vehicle(UAV)automatically positioning during power inspection,a visual positioning method which utilizes encoded sign as cooperative target is proposed.Firstly,we disc...In order to achieve the goal that unmanned aerial vehicle(UAV)automatically positioning during power inspection,a visual positioning method which utilizes encoded sign as cooperative target is proposed.Firstly,we discuss how to design the encoded sign and propose a robust decoding algorithm based on contour.Secondly,the Adaboost algorithm is used to train a classifier which can detect the encoded sign from image.Lastly,the position of UAV can be calculated by using the projective relation between the object points and their corresponding image points.Experiment includes two parts.First,simulated video data is used to verify the feasibility of the proposed method,and the results show that the average absolute error in each direction is below 0.02 m.Second,a video,acquired from an actual UAV flight,is used to calculate the position of UAV.The results show that the calculated trajectory is consistent with the actual flight path.The method runs at a speed of 0.153 sper frame.展开更多
An integration processing system of three-dimensional laser scanning information visualization in goaf was developed. It is provided with multiple functions, such as laser scanning information management for goaf, clo...An integration processing system of three-dimensional laser scanning information visualization in goaf was developed. It is provided with multiple functions, such as laser scanning information management for goaf, cloud data de-noising optimization, construction, display and operation of three-dimensional model, model editing, profile generation, calculation of goaf volume and roof area, Boolean calculation among models and interaction with the third party soft ware. Concerning this system with a concise interface, plentiful data input/output interfaces, it is featured with high integration, simple and convenient operations of applications. According to practice, in addition to being well-adapted, this system is favorably reliable and stable.展开更多
To study the effects of the initiation position on the damage and fracture characteristics of linear-charge blasting, blasting model experiments were conducted in this study using computed tomography scanning and thre...To study the effects of the initiation position on the damage and fracture characteristics of linear-charge blasting, blasting model experiments were conducted in this study using computed tomography scanning and three-dimensional reconstruction methods. The fractal damage theory was used to quantify the crack distribution and damage degree of sandstone specimens after blasting. The results showed that regardless of an inverse or top initiation, due to compression deformation and sliding frictional resistance, the plugging medium of the borehole is effective. The energy of the explosive gas near the top of the borehole is consumed. This affects the effective crushing of rocks near the top of the borehole, where the extent of damage to Sections Ⅰ and Ⅱ is less than that of Sections Ⅲ and Ⅳ. In addition, the analysis revealed that under conditions of top initiation, the reflected tensile damage of the rock at the free face of the top of the borehole and the compression deformation of the plug and friction consume more blasting energy, resulting in lower blasting energy efficiency for top initiation. As a result, the overall damage degree of the specimens in the top-initiation group was significantly smaller than that in the inverse-initiation group. Under conditions of inverse initiation, the blasting energy efficiency is greater, causing the specimen to experience greater damage. Therefore, in the engineering practice of rock tunnel cut blasting, to utilize blasting energy effectively and enhance the effects of rock fragmentation, using the inverse-initiation method is recommended. In addition, in three-dimensional(3D) rock blasting, the bottom of the borehole has obvious end effects under the conditions of inverse initiation, and the crack distribution at the bottom of the borehole is trumpet-shaped. The occurrence of an end effect in the 3D linear-charge blasting model experiment is related to the initiation position and the blocking condition.展开更多
Existing image captioning models usually build the relation between visual information and words to generate captions,which lack spatial infor-mation and object classes.To address the issue,we propose a novel Position...Existing image captioning models usually build the relation between visual information and words to generate captions,which lack spatial infor-mation and object classes.To address the issue,we propose a novel Position-Class Awareness Transformer(PCAT)network which can serve as a bridge between the visual features and captions by embedding spatial information and awareness of object classes.In our proposal,we construct our PCAT network by proposing a novel Grid Mapping Position Encoding(GMPE)method and refining the encoder-decoder framework.First,GMPE includes mapping the regions of objects to grids,calculating the relative distance among objects and quantization.Meanwhile,we also improve the Self-attention to adapt the GMPE.Then,we propose a Classes Semantic Quantization strategy to extract semantic information from the object classes,which is employed to facilitate embedding features and refining the encoder-decoder framework.To capture the interaction between multi-modal features,we propose Object Classes Awareness(OCA)to refine the encoder and decoder,namely OCAE and OCAD,respectively.Finally,we apply GMPE,OCAE and OCAD to form various combinations and to complete the entire PCAT.We utilize the MSCOCO dataset to evaluate the performance of our method.The results demonstrate that PCAT outperforms the other competitive methods.展开更多
Three-dimensional Information Decoupling System Based on PSD were designed based on LabVIEW, in order to achieve precision, timeliness, reliability require-ments of the PSD used in the ATP system of Satellite Earth qu...Three-dimensional Information Decoupling System Based on PSD were designed based on LabVIEW, in order to achieve precision, timeliness, reliability require-ments of the PSD used in the ATP system of Satellite Earth quantum communication. Firstly, the laser light source was driven by a stepper motor to scan on the PSD photosensitive surface, and the voltage value was collected and calculated to get the spot position. Analyzing the cause of nonlinear, a mathematical model was built between the actual value and the measured value by using binary quadratic polynomial method, PSD nonlinear correction function would be got. Then, the object micro displacement and angle offset were measured by combining optical triangulation method, and the error of the measurement results was corrected. Experimental results showed that, after the correction, the measuring deviation could be significantly reduced, the PSD performance calibration requirements was achieved, the efficiency of the system was developed greatly by using LabVIEW.展开更多
Transformers have been widely studied in many natural language processing (NLP) tasks, which can capture the dependency from the whole sentence with a high parallelizability thanks to the multi-head attention and the ...Transformers have been widely studied in many natural language processing (NLP) tasks, which can capture the dependency from the whole sentence with a high parallelizability thanks to the multi-head attention and the position-wise feed-forward network. However, the above two components of transformers are position-independent, which causes transformers to be weak in modeling sentence structures. Existing studies commonly utilized positional encoding or mask strategies for capturing the structural information of sentences. In this paper, we aim at strengthening the ability of transformers on modeling the linear structure of sentences from three aspects, containing the absolute position of tokens, the relative distance, and the direction between tokens. We propose a novel bidirectional Transformer with absolute-position aware relative position encoding (BiAR-Transformer) that combines the positional encoding and the mask strategy together. We model the relative distance between tokens along with the absolute position of tokens by a novel absolute-position aware relative position encoding. Meanwhile, we apply a bidirectional mask strategy for modeling the direction between tokens. Experimental results on the natural language inference, paraphrase identification, sentiment classification and machine translation tasks show that BiAR-Transformer achieves superior performance than other strong baselines.展开更多
基金supported by the Collaborative Tackling Project of the Yangtze River Delta SciTech Innovation Community(Nos.2024CSJGG01503,2024CSJGG01500)Guangxi Key Research and Development Program(No.AB24010317)Jiangxi Provincial Key Laboratory of Electronic Data Control and Forensics(Jiangxi Police College)(No.2025JXJYKFJJ002).
文摘Multimodal sentiment analysis aims to understand emotions from text,speech,and video data.However,current methods often overlook the dominant role of text and suffer from feature loss during integration.Given the varying importance of each modality across different contexts,a central and pressing challenge in multimodal sentiment analysis lies in maximizing the use of rich intra-modal features while minimizing information loss during the fusion process.In response to these critical limitations,we propose a novel framework that integrates spatial position encoding and fusion embedding modules to address these issues.In our model,text is treated as the core modality,while speech and video features are selectively incorporated through a unique position-aware fusion process.The spatial position encoding strategy preserves the internal structural information of speech and visual modalities,enabling the model to capture localized intra-modal dependencies that are often overlooked.This design enhances the richness and discriminative power of the fused representation,enabling more accurate and context-aware sentiment prediction.Finally,we conduct comprehensive evaluations on two widely recognized standard datasets in the field—CMU-MOSI and CMU-MOSEI to validate the performance of the proposed model.The experimental results demonstrate that our model exhibits good performance and effectiveness for sentiment analysis tasks.
基金supported by National Natural Science Foundation of China(Grant No.62073256)Shaanxi Provincial Science and Technology Department(Grant No.2023-YBGY-342)。
文摘To solve the problem of identification and measurement of two projectiles hitting the target at the same time,this paper proposes a projectile coordinate test method combining three photoelectric encoder detection screens,and establishes a coordinate calculation model for two projectiles to reach the same detection screen at the same time.The design method of three photoelectric encoder detection screens and the position coordinate recognition algorithm of the blocked array photoelectric detector when projectile passing through the photoelectric encoder detection screen are studied.Using the screen projection method,the intersected linear equation of the projectile and the line laser with the main detection screen as the core coordinate plane is established,and the projectile coordinate data set formed by any two photoelectric encoder detection screens is constructed.The principle of minimum error of coordinate data set is used to determine the coordinates of two projectiles hitting the target at the same time.The rationality and feasibility of the proposed test method are verified by experiments and comparative tests.
基金supported by the Natural Science Foundation of Shandong Province(ZR2021MA019)the National Natural Science Foundation of China(11871312)。
文摘In this paper,a composite numerical scheme is proposed to solve the threedimensional Darcy-Forchheimer miscible displacement problem with positive semi-definite assumptions.A mixed finite element is used for the fow equation.The velocity and pressure are computed simultaneously.The accuracy of velocity is improved one order.The concentration equation is solved by using mixed finite element,multi-step difference and upwind approximation.A multi-step method is used to approximate time derivative for improving the accuracy.The upwind approximation and an expanded mixed finite element are adopted to solve the convection and diffusion,respectively.The composite method could compute the diffusion flux and its gradient.It possibly becomes an eficient tool for solving convection-dominated diffusion problems.Firstly,the conservation of mass holds.Secondly,the multi-step method has high accuracy.Thirdly,the upwind approximation could avoid numerical dispersion.Using numerical analysis of a priori estimates and special techniques of differential equations,we give an error estimates for a positive definite problem.Numerical experiments illustrate its computational efficiency and feasibility of application.
基金supported by National Research Foundation of Singapore,AME Young Individual Research Grant(A2084c0167)。
文摘Accurate remaining useful life(RUL)prediction is important in industrial systems.It prevents machines from working under failure conditions,and ensures that the industrial system works reliably and efficiently.Recently,many deep learning based methods have been proposed to predict RUL.Among these methods,recurrent neural network(RNN)based approaches show a strong capability of capturing sequential information.This allows RNN based methods to perform better than convolutional neural network(CNN)based approaches on the RUL prediction task.In this paper,we question this common paradigm and argue that existing CNN based approaches are not designed according to the classic principles of CNN,which reduces their performances.Additionally,the capacity of capturing sequential information is highly affected by the receptive field of CNN,which is neglected by existing CNN based methods.To solve these problems,we propose a series of new CNNs,which show competitive results to RNN based methods.Compared with RNN,CNN processes the input signals in parallel so that the temporal sequence is not easily determined.To alleviate this issue,a position encoding scheme is developed to enhance the sequential information encoded by a CNN.Hence,our proposed position encoding based CNN called PE-Net is further improved and even performs better than RNN based methods.Extensive experiments are conducted on the C-MAPSS dataset,where our PE-Net shows state-of-the-art performance.
文摘A method and procedure is presented to reconstruct three-dimensional(3D) positions of scattering centers from multiple synthetic aperture radar(SAR) images. Firstly, two-dimensional(2D) attribute scattering centers of targets are extracted from 2D SAR images. Secondly, similarity measure is developed based on 2D attributed scatter centers' location, type, and radargrammetry principle between multiple SAR images. By this similarity, we can associate 2D scatter centers and then obtain candidate 3D scattering centers. Thirdly, these candidate scattering centers are clustered in 3D space to reconstruct final 3D positions. Compared with presented methods, the proposed method has a capability of describing distributed scattering center, reduces false and missing 3D scattering centers, and has fewer restrictionson modeling data. Finally, results of experiments have demonstrated the effectiveness of the proposed method.
基金This work was supported by Natural Science Foundation of Hainan Province of China(No.117212)National Natural Science Foundation of China(Nos.61633008,61374007,61601262 and 61701487)Natural Science Foundation of Heilongjiang Province of China(No.F2017005)and China Scholarship Council.
文摘This paper addresses the problem of assessing and optimizing the acoustic positioning system for underwater target localization with range measurement.We present a new three-dimensional assessment model to evaluate the optimal geometric beacon formation whether meets user requirements.For mathematical tractability,it is assumed that the measurements of the range between the target and beacons are corrupted with white Gaussian noise with variance,which is distance-dependent.Then,the relationship between DOP parameters and positioning accuracy can be derived by adopting dilution of precision(DOP)parameters in the assessment model.In addition,the optimal geometric beacon formation yielding the best performance can be achieved via minimizing the values of geometric dilution of precision(GDOP)in the case where the target position is known and fixed.Next,in order to ensure that the estimated positioning accuracy on the region of interest satisfies the precision required by the user,geometric positioning accuracy(GPA),horizontal positioning accuracy(HPA)and vertical positioning accuracy(VPA)are utilized to assess the optimal geometric beacon formation.Simulation examples are designed to illustrate the exactness of the conclusion.Unlike other work that only uses GDOP to optimize the formation and cannot assess the performance of the specified size,this new three-dimensional assessment model can evaluate the optimal geometric beacon formation for each dimension of any point in three-dimensional space,which can provide guidance to optimize the performance of each specified dimension.
基金supported by the National Key Research Projects(No.2016YFB0501403)the National Demonstration Center for Experimental Remote Sensing&Information Engineering(Wuhan University)
文摘In order to achieve the goal that unmanned aerial vehicle(UAV)automatically positioning during power inspection,a visual positioning method which utilizes encoded sign as cooperative target is proposed.Firstly,we discuss how to design the encoded sign and propose a robust decoding algorithm based on contour.Secondly,the Adaboost algorithm is used to train a classifier which can detect the encoded sign from image.Lastly,the position of UAV can be calculated by using the projective relation between the object points and their corresponding image points.Experiment includes two parts.First,simulated video data is used to verify the feasibility of the proposed method,and the results show that the average absolute error in each direction is below 0.02 m.Second,a video,acquired from an actual UAV flight,is used to calculate the position of UAV.The results show that the calculated trajectory is consistent with the actual flight path.The method runs at a speed of 0.153 sper frame.
基金Project(51274250)supported by the National Natural Science Foundation of ChinaProject(2012BAK09B02-05)supported by the National Key Technology R&D Program during the 12th Five-year Plan of China
文摘An integration processing system of three-dimensional laser scanning information visualization in goaf was developed. It is provided with multiple functions, such as laser scanning information management for goaf, cloud data de-noising optimization, construction, display and operation of three-dimensional model, model editing, profile generation, calculation of goaf volume and roof area, Boolean calculation among models and interaction with the third party soft ware. Concerning this system with a concise interface, plentiful data input/output interfaces, it is featured with high integration, simple and convenient operations of applications. According to practice, in addition to being well-adapted, this system is favorably reliable and stable.
基金supported by the National Natural Science Foundation of China (No.52204085)the Interdisciplinary Research Project for Young Teachers of USTB,Fundamental Research Funds for the Central Universities (No.FRF-IDRY-21-006).
文摘To study the effects of the initiation position on the damage and fracture characteristics of linear-charge blasting, blasting model experiments were conducted in this study using computed tomography scanning and three-dimensional reconstruction methods. The fractal damage theory was used to quantify the crack distribution and damage degree of sandstone specimens after blasting. The results showed that regardless of an inverse or top initiation, due to compression deformation and sliding frictional resistance, the plugging medium of the borehole is effective. The energy of the explosive gas near the top of the borehole is consumed. This affects the effective crushing of rocks near the top of the borehole, where the extent of damage to Sections Ⅰ and Ⅱ is less than that of Sections Ⅲ and Ⅳ. In addition, the analysis revealed that under conditions of top initiation, the reflected tensile damage of the rock at the free face of the top of the borehole and the compression deformation of the plug and friction consume more blasting energy, resulting in lower blasting energy efficiency for top initiation. As a result, the overall damage degree of the specimens in the top-initiation group was significantly smaller than that in the inverse-initiation group. Under conditions of inverse initiation, the blasting energy efficiency is greater, causing the specimen to experience greater damage. Therefore, in the engineering practice of rock tunnel cut blasting, to utilize blasting energy effectively and enhance the effects of rock fragmentation, using the inverse-initiation method is recommended. In addition, in three-dimensional(3D) rock blasting, the bottom of the borehole has obvious end effects under the conditions of inverse initiation, and the crack distribution at the bottom of the borehole is trumpet-shaped. The occurrence of an end effect in the 3D linear-charge blasting model experiment is related to the initiation position and the blocking condition.
基金supported by the National Key Research and Development Program of China[No.2021YFB2206200].
文摘Existing image captioning models usually build the relation between visual information and words to generate captions,which lack spatial infor-mation and object classes.To address the issue,we propose a novel Position-Class Awareness Transformer(PCAT)network which can serve as a bridge between the visual features and captions by embedding spatial information and awareness of object classes.In our proposal,we construct our PCAT network by proposing a novel Grid Mapping Position Encoding(GMPE)method and refining the encoder-decoder framework.First,GMPE includes mapping the regions of objects to grids,calculating the relative distance among objects and quantization.Meanwhile,we also improve the Self-attention to adapt the GMPE.Then,we propose a Classes Semantic Quantization strategy to extract semantic information from the object classes,which is employed to facilitate embedding features and refining the encoder-decoder framework.To capture the interaction between multi-modal features,we propose Object Classes Awareness(OCA)to refine the encoder and decoder,namely OCAE and OCAD,respectively.Finally,we apply GMPE,OCAE and OCAD to form various combinations and to complete the entire PCAT.We utilize the MSCOCO dataset to evaluate the performance of our method.The results demonstrate that PCAT outperforms the other competitive methods.
文摘Three-dimensional Information Decoupling System Based on PSD were designed based on LabVIEW, in order to achieve precision, timeliness, reliability require-ments of the PSD used in the ATP system of Satellite Earth quantum communication. Firstly, the laser light source was driven by a stepper motor to scan on the PSD photosensitive surface, and the voltage value was collected and calculated to get the spot position. Analyzing the cause of nonlinear, a mathematical model was built between the actual value and the measured value by using binary quadratic polynomial method, PSD nonlinear correction function would be got. Then, the object micro displacement and angle offset were measured by combining optical triangulation method, and the error of the measurement results was corrected. Experimental results showed that, after the correction, the measuring deviation could be significantly reduced, the PSD performance calibration requirements was achieved, the efficiency of the system was developed greatly by using LabVIEW.
基金supported by the Key Development Program of the Ministry of Science and Technology(2019YFF0303003)the National Natural Science Foundation of China(Grant No.61976068)“Hundreds,Millions”Engineering Science and Technology Major Special Project of Heilongjiang Province(2020ZX14A02).
文摘Transformers have been widely studied in many natural language processing (NLP) tasks, which can capture the dependency from the whole sentence with a high parallelizability thanks to the multi-head attention and the position-wise feed-forward network. However, the above two components of transformers are position-independent, which causes transformers to be weak in modeling sentence structures. Existing studies commonly utilized positional encoding or mask strategies for capturing the structural information of sentences. In this paper, we aim at strengthening the ability of transformers on modeling the linear structure of sentences from three aspects, containing the absolute position of tokens, the relative distance, and the direction between tokens. We propose a novel bidirectional Transformer with absolute-position aware relative position encoding (BiAR-Transformer) that combines the positional encoding and the mask strategy together. We model the relative distance between tokens along with the absolute position of tokens by a novel absolute-position aware relative position encoding. Meanwhile, we apply a bidirectional mask strategy for modeling the direction between tokens. Experimental results on the natural language inference, paraphrase identification, sentiment classification and machine translation tasks show that BiAR-Transformer achieves superior performance than other strong baselines.
